Rounding-based Moves for Semi-Metric Labeling

Abstract : Semi-metric labeling is a special case of energy minimization for pairwise Markov random fields. The energy function consists of arbitrary unary potentials, and pairwise potentials that are proportional to a given semi-metric distance function over the label set. Popular methods for solving semi-metric labeling include (i) move-making algorithms, which iteratively solve a minimum st-cut problem; and (ii) the linear programming (LP) relaxation based approach. In order to convert the fractional solution of the LP relaxation to an integer solution, several randomized rounding procedures have been developed in the literature. We consider a large class of parallel rounding procedures, and design move-making algorithms that closely mimic them. We prove that the multiplicative bound of a move-making algorithm exactly matches the approximation factor of the corresponding rounding procedure for any arbitrary distance function. Our analysis includes all known results for move-making algorithms as special cases.
Type de document :
Article dans une revue
Journal of Machine Learning Research, Journal of Machine Learning Research, 2016, 17, pp.1 - 42
Liste complète des métadonnées


https://hal.inria.fr/hal-01577719
Contributeur : Puneet Kumar Dokania <>
Soumis le : dimanche 27 août 2017 - 23:45:22
Dernière modification le : mercredi 30 août 2017 - 01:08:34

Fichier

14-454.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01577719, version 1

Citation

M. Pawan Kumar, Puneet K. Dokania. Rounding-based Moves for Semi-Metric Labeling . Journal of Machine Learning Research, Journal of Machine Learning Research, 2016, 17, pp.1 - 42. <hal-01577719>

Partager

Métriques

Consultations de
la notice

56

Téléchargements du document

10